object detection API 制作自己的数据集

1.数据标注
使用labelImg对图片进行标注，标注后生成 .xml 格式文件，含有图像格式尺寸，标签，坐标的相应内容。如果想要去除文件中的某类标签，可以使用xml.etree.ElementTree库来帮助完成。
2.制作数据集
新建文件夹名为data set，该文件夹下有两个文件夹images（存放图片）和xml_file（存放标注文件），新建文件夹Annotations，该文件夹内有train，val，test三个空文件夹。

执行下面的代码，对xml文件进行随机分配

import os  
import random  
import time  
import shutil  
  
xmlfilepath=r'H:\data set\xml_file'
os.chdir('H:\data set')  
saveBasePath=r"./Annotations"  
  
trainval_percent=0.9  
train_percent=0.85  
total_xml = os.listdir(xmlfilepath)  
num=len(total_xml)  
list=range(num)  
tv=int(num*trainval_percent)  
tr=int(tv*train_percent)  
trainval= random.sample(list,tv)  
train=random.sample(trainval,tr)  
  
print("train and val size",tv)  
print("train size",tr)  
start = time.time()  
  
test_num=0  
val_num=0  
train_num=0  
 
for i  in list:  
    name=total_xml[i]    
    if i in trainval:  
        if i in train:  
            directory="train"  
            train_num+=1  
            xml_path = os.path.join(os.getcwd(), 'Annotations/{}'.format(directory))  
            if(not os.path.exists(xml_path)):  
                os.mkdir(xml_path)  
            filePath=os.path.join(xmlfilepath,name)  
            newfile=os.path.join(saveBasePath,os.path.join(directory,name))  
            shutil.copyfile(filePath, newfile)  
  
        else:  
            directory="val"  
            xml_path = os.path.join(os.getcwd(), 'Annotations/{}'.format(directory))  
            if(not os.path.exists(xml_path)):  
                os.mkdir(xml_path)  
            val_num+=1  
            filePath=os.path.join(xmlfilepath,name)  
            newfile=os.path.join(saveBasePath,os.path.join(directory,name))  
            shutil.copyfile(filePath, newfile)  
    else: 
        directory="test"  
        xml_path = os.path.join(os.getcwd(), 'Annotations/{}'.format(directory))  
        if(not os.path.exists(xml_path)):  
            os.mkdir(xml_path)  
        test_num+=1  
        filePath=os.path.join(xmlfilepath,name)  
        newfile=os.path.join(saveBasePath,os.path.join(directory,name))  
        shutil.copyfile(filePath, newfile)  
  
end = time.time()  
seconds=end-start  
print("train total : "+str(train_num))  
print("val total : "+str(val_num))  
print("test total : "+str(test_num))  
total_num=train_num+val_num+test_num  
print("total number : "+str(total_num))  
print( "Time taken : {0} seconds".format(seconds))

新建csv文件夹执行下面代码将xml存储在csv中。我在标注图片时发现一部分的xml文件中文件名格式不统一，有的含有,jpg有的不含，所以对代码进行了略微改动，不需要的人可以去掉。

import os
import glob
import pandas as pd
import xml.etree.ElementTree as ET
 
def xml_to_csv(path):
    xml_list = []
    for xml_file in glob.glob(path + '/*.xml'):
        tree = ET.parse(xml_file)
        root = tree.getroot()
 #       print(root.find('filename').text)
        filename2=root.find('filename').text
        filename3=os.path.splitext(filename2)[0]
        filename4=filename3+'.jpg'
        print(filename4)
        for member in root.findall('object'):
            value = (filename4,
                     int(root.find('size')[1].text),   #width
                     int(root.find('size')[2].text),   #height
                     member[0].text,
                     int(member[4][0].text),
                     int(float(member[4][1].text)),
                     int(member[4][2].text),
                     int(member[4][3].text)
                     )
            xml_list.append(value)
    column_name = ['filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax']
    xml_df = pd.DataFrame(xml_list, columns=column_name)
    return xml_df
 
def main():
    for directory in ['train','test','val']:
        xml_path = os.path.join(os.getcwd(), 'Annotations/{}'.format(directory))
        xml_df = xml_to_csv(xml_path)
        xml_df.to_csv('csv/damage_{}_labels.csv'.format(directory), index=None)
        print('Successfully converted xml to csv.')
 
main()

新建.py文件将csv转化为tfrecord

from __future__ import division
from __future__ import print_function
from __future__ import absolute_import
 
import os
import io
import pandas as pd
import tensorflow as tf


from PIL import Image
from object_detection.utils import dataset_util
from collections import namedtuple, OrderedDict
 
flags = tf.app.flags
flags.DEFINE_string('csv_input', '', 'Path to the CSV input')
flags.DEFINE_string('output_path', '', 'Path to output TFRecord')
FLAGS = flags.FLAGS
 
 
# 要改成自己的标签名称
def class_text_to_int(row_label):
    if row_label == 'xxx':
        return 1
    elif row_label == 'yyy':
        return 2 
    else:
        return 0
 
 
def split(df, group):
    data = namedtuple('data', ['filename', 'object'])
    gb = df.groupby(group)
    return [data(filename, gb.get_group(x)) for filename, x in zip(gb.groups.keys(), gb.groups)]
 
 
def create_tf_example(group, path):
    with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)), 'rb') as fid:
        encoded_jpg = fid.read()
    encoded_jpg_io = io.BytesIO(encoded_jpg)
    image = Image.open(encoded_jpg_io)
    width, height = image.size
 
    filename = group.filename.encode('utf8')
    image_format = b'jpg'
    xmins = []
    xmaxs = []
    ymins = []
    ymaxs = []
    classes_text = []
    classes = []
 
    for index, row in group.object.iterrows():
        xmins.append(row['xmin'] / width)
        xmaxs.append(row['xmax'] / width)
        ymins.append(row['ymin'] / height)
        ymaxs.append(row['ymax'] / height)
        classes_text.append(row['class'].encode('utf8'))
        classes.append(class_text_to_int(row['class']))
 
    tf_example = tf.train.Example(features=tf.train.Features(feature={
        'image/height': dataset_util.int64_feature(height),
        'image/width': dataset_util.int64_feature(width),
        'image/filename': dataset_util.bytes_feature(filename),
        'image/source_id': dataset_util.bytes_feature(filename),
        'image/encoded': dataset_util.bytes_feature(encoded_jpg),
        'image/format': dataset_util.bytes_feature(image_format),
        'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
        'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
        'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
        'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
        'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
        'image/object/class/label': dataset_util.int64_list_feature(classes),
    }))
    return tf_example
 
 
def main(_):
    writer = tf.python_io.TFRecordWriter(FLAGS.output_path)
    path = os.path.join(os.getcwd(), 'images')
    examples = pd.read_csv(FLAGS.csv_input)
    grouped = split(examples, 'filename')
    num=0
    for group in grouped:
        num+=1
        tf_example = create_tf_example(group, path)
        writer.write(tf_example.SerializeToString())
        print(num)
 
    writer.close()
    output_path = os.path.join(os.getcwd(), FLAGS.output_path)
    print('Successfully created the TFRecords: {}'.format(output_path))
 
 
if __name__ == '__main__':
    tf.app.run()

然后在该文件夹下使用下列命令生成文件
python csvTotfrecord.py --csv_input=csv/train_labels.csv --output_path=csv/train.tfrecord

最后需要新建.pbtxt的标签文件，写入类别标签

item {
	id: 1
	name: 'xxx'
}

item {
	id: 2
	name: 'yyy'
}

3.模型训练
在/object_detection/samples/configs/下找到config文件，修改里面的类别数，4个文件地址，其余部分依照各自需求进行修改即可。例如是否fineturn，训练步长，学习率，保存步长等等内容。有的需要在model_main.py文件中修改。
最后开始训练即可。